Scholarlink

<p>In this paper, we develop efficient numerical methods and a general framework, based on AI technologies, to solve for financial derivatives prices and Greeks in a real-time manner. Our methodologies extend the traditional path derivative, likelihood ratio and finite difference approaches, making full use of machine learning techniques, and are able to produce fast and accurate estimates of financial derivative prices and risk-factor sensitivity metrics such as Delta, Gamma, Rho and Vega. The machine learning based computational framework proposed is of both theoretical and practical interest and is readily applicable to day-to-day business. Moreover, we propose a state-of-the-art way for model parameter inference.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A general machine learning framework of real-time evaluation for financial derivatives portfolios

  • 期刊论文

  • 发表日期：

    2025年6月8日

查看全文
  • Liangliang Zhang,
  • Ruyan Tian,
  • Qing Yang,
  • Tingting Ye

摘要

In this paper, we develop efficient numerical methods and a general framework, based on AI technologies, to solve for financial derivatives prices and Greeks in a real-time manner. Our methodologies extend the traditional path derivative, likelihood ratio and finite difference approaches, making full use of machine learning techniques, and are able to produce fast and accurate estimates of financial derivative prices and risk-factor sensitivity metrics such as Delta, Gamma, Rho and Vega. The machine learning based computational framework proposed is of both theoretical and practical interest and is readily applicable to day-to-day business. Moreover, we propose a state-of-the-art way for model parameter inference.